Book Title: Applied Artificial Intelligence: From Fundamentals to Real-World AI Systems

Book Description

Applied Artificial Intelligence: From Fundamentals to Real-World AI Systems provides a practical introduction to modern artificial intelligence through a systems-oriented, learning-by-building approach. Designed for undergraduate and introductory graduate students, the book begins with AI foundations, machine learning, deep learning, probability, statistics, and experimental design before progressing to generative AI, large language models, retrieval-augmented generation, and agentic AI systems.

Rather than focusing only on algorithms, the book teaches students to think about the complete AI system: the task being solved, the model or method, the surrounding software, evaluation metrics, data pipelines, security boundaries, reliability, human oversight, and deployment constraints. Students work through Python examples, debugging exercises, review questions, mini-projects, and graduate research extensions that emphasize evidence, reproducibility, baselines, ablation studies, and failure analysis.

Later chapters examine AI applications in cybersecurity, robotics, healthcare, software engineering, education, scientific research, and embedded systems, followed by responsible and trustworthy AI, research methodology, and six substantial capstone project families. Supporting appendices provide Python references, mathematics for AI, evaluation metrics, LLM/RAG/agent checklists, reproducibility guidance, environment setup, recommended libraries, and a suggested semester course plan.

The goal is not to present every AI technique in isolation, but to help learners understand how modern AI components work together and how to evaluate whether an AI system actually performs its intended task reliably and responsibly.